Skip to content

Conversation

@CUHKSZzxy
Copy link
Collaborator

Although vLLM use the exactly this function, but seems producing different results compared to HF code. Potentially leads to acc misalignment.

@CUHKSZzxy CUHKSZzxy closed this Dec 25, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant